@inproceedings{reynaert-etal-2012-beyond,
title = "Beyond {S}o{N}a{R}: towards the facilitation of large corpus building efforts",
author = "Reynaert, Martin and
Schuurman, Ineke and
Hoste, V{\'e}ronique and
Oostdijk, Nelleke and
van Gompel, Maarten",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/748_Paper.pdf",
pages = "2897--2904",
abstract = "In this paper we report on the experiences gained in the recent construction of the SoNaR corpus, a 500 MW reference corpus of contemporary, written Dutch. It shows what can realistically be done within the confines of a project setting where there are limitations to the duration in time as well to the budget, employing current state-of-the-art tools, standards and best practices. By doing so we aim to pass on insights that may be beneficial for anyone considering to undertake an effort towards building a large, varied yet balanced corpus for use by the wider research community. Various issues are discussed that come into play while compiling a large corpus, including approaches to acquiring texts, the arrangement of IPR, the choice of text formats, and steps to be taken in the preprocessing of data from widely different origins. We describe FoLiA, a new XML format geared at rich linguistic annotations. We also explain the rationale behind the investment in the high-quali ty semi-automatic enrichment of a relatively small (1 MW) subset with very rich syntactic and semantic annotations. Finally, we present some ideas about future developments and the direction corpus development may take, such as setting up an integrated work flow between web services and the potential role for ISOcat. We list tips for potential corpus builders, tricks they may want to try and further recommendations regarding technical developments future corpus builders may wish to hope for.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reynaert-etal-2012-beyond">
<titleInfo>
<title>Beyond SoNaR: towards the facilitation of large corpus building efforts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Reynaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ineke</namePart>
<namePart type="family">Schuurman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Véronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelleke</namePart>
<namePart type="family">Oostdijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarten</namePart>
<namePart type="family">van Gompel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we report on the experiences gained in the recent construction of the SoNaR corpus, a 500 MW reference corpus of contemporary, written Dutch. It shows what can realistically be done within the confines of a project setting where there are limitations to the duration in time as well to the budget, employing current state-of-the-art tools, standards and best practices. By doing so we aim to pass on insights that may be beneficial for anyone considering to undertake an effort towards building a large, varied yet balanced corpus for use by the wider research community. Various issues are discussed that come into play while compiling a large corpus, including approaches to acquiring texts, the arrangement of IPR, the choice of text formats, and steps to be taken in the preprocessing of data from widely different origins. We describe FoLiA, a new XML format geared at rich linguistic annotations. We also explain the rationale behind the investment in the high-quali ty semi-automatic enrichment of a relatively small (1 MW) subset with very rich syntactic and semantic annotations. Finally, we present some ideas about future developments and the direction corpus development may take, such as setting up an integrated work flow between web services and the potential role for ISOcat. We list tips for potential corpus builders, tricks they may want to try and further recommendations regarding technical developments future corpus builders may wish to hope for.</abstract>
<identifier type="citekey">reynaert-etal-2012-beyond</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/748_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2897</start>
<end>2904</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond SoNaR: towards the facilitation of large corpus building efforts
%A Reynaert, Martin
%A Schuurman, Ineke
%A Hoste, Véronique
%A Oostdijk, Nelleke
%A van Gompel, Maarten
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F reynaert-etal-2012-beyond
%X In this paper we report on the experiences gained in the recent construction of the SoNaR corpus, a 500 MW reference corpus of contemporary, written Dutch. It shows what can realistically be done within the confines of a project setting where there are limitations to the duration in time as well to the budget, employing current state-of-the-art tools, standards and best practices. By doing so we aim to pass on insights that may be beneficial for anyone considering to undertake an effort towards building a large, varied yet balanced corpus for use by the wider research community. Various issues are discussed that come into play while compiling a large corpus, including approaches to acquiring texts, the arrangement of IPR, the choice of text formats, and steps to be taken in the preprocessing of data from widely different origins. We describe FoLiA, a new XML format geared at rich linguistic annotations. We also explain the rationale behind the investment in the high-quali ty semi-automatic enrichment of a relatively small (1 MW) subset with very rich syntactic and semantic annotations. Finally, we present some ideas about future developments and the direction corpus development may take, such as setting up an integrated work flow between web services and the potential role for ISOcat. We list tips for potential corpus builders, tricks they may want to try and further recommendations regarding technical developments future corpus builders may wish to hope for.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/748_Paper.pdf
%P 2897-2904
Markdown (Informal)
[Beyond SoNaR: towards the facilitation of large corpus building efforts](http://www.lrec-conf.org/proceedings/lrec2012/pdf/748_Paper.pdf) (Reynaert et al., LREC 2012)
ACL
- Martin Reynaert, Ineke Schuurman, Véronique Hoste, Nelleke Oostdijk, and Maarten van Gompel. 2012. Beyond SoNaR: towards the facilitation of large corpus building efforts. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2897–2904, Istanbul, Turkey. European Language Resources Association (ELRA).